Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 725 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2644. Min Act: -0.1700

Data Index: 2229590 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2823. Min Act: -0.1700

Data Index: 5538954 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2078. Min Act: -0.1700

Data Index: 1521226 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2043. Min Act: -0.1700

Data Index: 1071279 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2084. Min Act: -0.1700

Data Index: 246673 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2235. Min Act: -0.1700

Data Index: 4594586 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1708. Min Act: -0.1700

Data Index: 8312708 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1652. Min Act: -0.1700

Data Index: 211572 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1603. Min Act: -0.1700

Data Index: 3991528 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1619. Min Act: -0.1700

Data Index: 1457125 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1564. Min Act: -0.1700

Data Index: 8088286 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1745. Min Act: -0.1700

Data Index: 6371007 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1671. Min Act: -0.1700

Data Index: 5491761 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1558. Min Act: -0.1700

Data Index: 5415900 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1739. Min Act: -0.1700

Data Index: 4985017 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1482. Min Act: -0.1700

Data Index: 3817879 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1374. Min Act: -0.1700

Data Index: 3829515 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1302. Min Act: -0.1700

Data Index: 4091079 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1477. Min Act: -0.1700

Data Index: 1803810 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1417. Min Act: -0.1700

Data Index: 1952445 (Open Web Text)

Max Activating Token Index: 4